Back to the Color: Learning Depth to Specific Color Transformation for Unsupervised Depth Estimation

• URL: http://arxiv.org/abs/2406.07741v6
• Date: Tue, 15 Oct 2024 07:27:28 GMT
• Title: Back to the Color: Learning Depth to Specific Color Transformation for Unsupervised Depth Estimation
• Authors: Yufan Zhu, Chongzhi Ran, Mingtao Feng, Fangfang Wu, Le Dong, Weisheng Dong, Antonio M. López, Guangming Shi,
• Abstract summary: discrepancies between synthetic and real-world colors pose significant challenges for depth estimation in real-world scenes. We propose Back2Color, a framework that predicts realistic colors from depth using a model trained on real-world data. We also present VADepth, based on the Vision Attention Network, which offers lower computational complexity and higher accuracy than transformers.
• Score: 45.07558105128673
• License:
• Abstract: Virtual engines can generate dense depth maps for various synthetic scenes, making them invaluable for training depth estimation models. However, discrepancies between synthetic and real-world colors pose significant challenges for depth estimation in real-world scenes, especially in complex and uncertain environments encountered in unsupervised monocular depth estimation tasks. To address this issue, we propose Back2Color, a framework that predicts realistic colors from depth using a model trained on real-world data, thus transforming synthetic colors into their real-world counterparts. Additionally, we introduce the Syn-Real CutMix method for joint training with both real-world unsupervised and synthetic supervised depth samples, enhancing monocular depth estimation performance in real-world scenes. Furthermore, to mitigate the impact of non-rigid motions on depth estimation, we present an auto-learning uncertainty temporal-spatial fusion method (Auto-UTSF), which leverages the strengths of unsupervised learning in both temporal and spatial dimensions. We also designed VADepth, based on the Vision Attention Network, which offers lower computational complexity and higher accuracy than transformers. Our Back2Color framework achieves state-of-the-art performance on the Kitti dataset, as evidenced by improvements in performance metrics and the production of fine-grained details. This is particularly evident on more challenging datasets such as Cityscapes for unsupervised depth estimation.

Related papers

• MetricGold: Leveraging Text-To-Image Latent Diffusion Models for Metric Depth Estimation [9.639797094021988]
  MetricGold is a novel approach that harnesses generative diffusion model's rich priors to improve metric depth estimation. Our experiments demonstrate robust generalization across diverse datasets, producing sharper and higher quality metric depth estimates.
  arXiv  Detail & Related papers  (2024-11-16T20:59:01Z)
• Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering [93.94371335579321]
  We propose a learning framework that trains models to predict geometry-preserving depth without requiring extra data or annotations. Comprehensive experiments underscore our framework's superior generalization capabilities. Our innovative loss functions empower the model to autonomously recover domain-specific scale-and-shift coefficients.
  arXiv  Detail & Related papers  (2023-09-18T12:36:39Z)
• DEHRFormer: Real-time Transformer for Depth Estimation and Haze Removal from Varicolored Haze Scenes [10.174140482558904]
  We propose a real-time transformer for simultaneous single image Depth Estimation and Haze Removal. DEHRFormer consists of a single encoder and two task-specific decoders. We introduce a novel learning paradigm that utilizes contrastive learning and domain consistency learning to tackle weak-generalization problem for real-world dehazing.
  arXiv  Detail & Related papers  (2023-03-13T07:47:18Z)
• SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic Scenes [58.89295356901823]
  Self-supervised monocular depth estimation has shown impressive results in static scenes. It relies on the multi-view consistency assumption for training networks, however, that is violated in dynamic object regions. We introduce an external pretrained monocular depth estimation model for generating single-image depth prior. Our model can predict sharp and accurate depth maps, even when training from monocular videos of highly-dynamic scenes.
  arXiv  Detail & Related papers  (2022-11-07T16:17:47Z)
• Unsupervised Single-shot Depth Estimation using Perceptual Reconstruction [0.0]
  This study presents the most recent advances in the field of generative neural networks, leveraging them to perform fully unsupervised single-shot depth synthesis. Two generators for RGB-to-depth and depth-to-RGB transfer are implemented and simultaneously optimized using the Wasserstein-1 distance and a novel perceptual reconstruction term. The success observed in this study suggests the great potential for unsupervised single-shot depth estimation in real-world applications.
  arXiv  Detail & Related papers  (2022-01-28T15:11:34Z)
• Occlusion-aware Unsupervised Learning of Depth from 4-D Light Fields [50.435129905215284]
  We present an unsupervised learning-based depth estimation method for 4-D light field processing and analysis. Based on the basic knowledge of the unique geometry structure of light field data, we explore the angular coherence among subsets of the light field views to estimate depth maps. Our method can significantly shrink the performance gap between the previous unsupervised method and supervised ones, and produce depth maps with comparable accuracy to traditional methods with obviously reduced computational cost.
  arXiv  Detail & Related papers  (2021-06-06T06:19:50Z)
• Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors [67.88097893304274]
  We propose a human volumetric capture method that combines temporal fusion and deep implicit functions. We propose dynamic sliding to fuse depth observations together with topology consistency.
  arXiv  Detail & Related papers  (2021-05-05T04:12:38Z)
• Domain Adaptive Monocular Depth Estimation With Semantic Information [13.387521845596149]
  We propose an adversarial training model that leverages semantic information to narrow the domain gap. The proposed compact model achieves state-of-the-art performance comparable to complex latest models.
  arXiv  Detail & Related papers  (2021-04-12T18:50:41Z)
• Unpaired Single-Image Depth Synthesis with cycle-consistent Wasserstein GANs [1.0499611180329802]
  Real-time estimation of actual environment depth is an essential module for various autonomous system tasks. In this study, latest advancements in the field of generative neural networks are leveraged to fully unsupervised single-image depth synthesis.
  arXiv  Detail & Related papers  (2021-03-31T09:43:38Z)
• DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation Learning [65.94499390875046]
  DeFeat-Net is an approach to simultaneously learn a cross-domain dense feature representation. Our technique is able to outperform the current state-of-the-art with around 10% reduction in all error measures.
  arXiv  Detail & Related papers  (2020-03-30T13:10:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.